© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14717
    Prev
    Next
    INDEX
    Explanations

    betting odds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hollow
    -0.20
    æĢ»æĶ¶åħ¥
    -0.20
    èĩ³ä¸Ĭ
    -0.19
    cÃŃ
    -0.18
    åĩºéĻ¢
    -0.18
     Recycling
    -0.18
     Sabha
    -0.18
    izons
    -0.18
    åĪĿæģĭ
    -0.18
     Joi
    -0.17
    POSITIVE LOGITS
    é¢Ħæµĭ
    0.29
    èµĶ
    0.29
     betting
    0.26
    æĬ¼
    0.26
    Prediction
    0.25
     prediction
    0.25
    æĬķ注
    0.24
    票
    0.23
    é¢Ħè¨Ģ
    0.23
    æĬ¥ä»·
    0.22
    Activations Density 0.050%

    No Known Activations